tidypr-1.5b-gguf is an open-weight model from Harsh, released under Apache License 2.0. Its published files total 2.6 GB. It draws 254 downloads a month.
Fine-tune of unsloth/Qwen2.5-Coder-1.5B-Instruct that flags AI slop (over-defensive code, redundant comments, filler docstrings, emoji logs, placeholder TODOs…) in Python pull-request hunks and returns JSON findings. Built with tidypr.
Model Card
By Harsh, published under apache-2.0, revision 1c9f1e405e6e.
Fine-tune of unsloth/Qwen2.5-Coder-1.5B-Instruct that flags AI slop (over-defensive code, redundant comments, filler docstrings, emoji logs, placeholder TODOs…) in Python pull-request hunks and returns JSON findings. Built with tidypr. Use it in a PR: LoRA fine-tune (Unsloth, QLoRA) on a mix of: - inline review comments from humans on AI-agent pull requests (AIDev), and review comments from CodeReviewer, turned into labels by a Qwen2.5-Coder-7B teacher - hunks reviewers accepted without comment (CodeReviewer) - synthetic slop injected into human-written Python (CPython standard library) Weights: Apache-2.0, same as the base model unsloth/Qwen2.5-Coder-1.5B-Instruct. Code: MIT (tidypr). The…
Read Harsh's full model card
Fine-tune of unsloth/Qwen2.5-Coder-1.5B-Instruct that flags AI slop (over-defensive code, redundant comments, filler
docstrings, emoji logs, placeholder TODOs…) in Python pull-request hunks and returns JSON findings.
Built with tidypr. Use it in a PR:
- uses: thebunnyweb/tidypr@v0
with:
model: bunnyweb/tidypr-1.5b-gguf
Locally:
pip install "tidypr[infer]"
git diff main... | tidypr review --diff - --backend llamacpp --model bunnyweb/tidypr-1.5b-gguf
Training data
LoRA fine-tune (Unsloth, QLoRA) on a mix of: - inline review comments from humans on AI-agent pull requests (AIDev), and review comments from CodeReviewer, turned into labels by a Qwen2.5-Coder-7B teacher - hunks reviewers accepted without comment (CodeReviewer) - synthetic slop injected into human-written Python (CPython standard library)
License
Weights: Apache-2.0, same as the base model unsloth/Qwen2.5-Coder-1.5B-Instruct. Code: MIT (tidypr).
The training data contains third-party code under its original licenses and is not redistributed.
Status: early. Check the repo's eval report before trusting it; categories that miss the precision bar are off by default.
Identity and Version
- Repository
- bunnyweb/tidypr-1.5b-gguf
- Publisher
- Harsh
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- 1c9f1e405e6e39bb1655f325279f58dc73d86125
- First published
- 2026-10-11
- Last updated
- 2026-10-14
Files and Weights
4 files, 2.6 GB in total. The weights are 2 files totalling 2.6 GB in gguf.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| Qwen2.5-Coder-1.5B-Instruct.Q4_K_M.gguf | Weights | 986.0 MB | 1c398f16a406 |
| Qwen2.5-Coder-1.5B-Instruct.Q8_0.gguf | Weights | 1.6 GB | f9eda3130cb0 |
| README.md | Documentation | 1.5 KB | — |
| .gitattributes | Repository | 1.7 KB | — |
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
- Download size
- 2.6 GB
Released by Harsh through its official repository on Hugging Face. Read the license.
Built From
- Adapter of unsloth/Qwen2.5-Coder-1.5B-Instruct
- Derived from unsloth/Qwen2.5-Coder-1.5B-Instruct
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 2.6 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About tidypr-1.5b-gguf
Can I use tidypr-1.5b-gguf commercially?
Yes. tidypr-1.5b-gguf is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.